[robinvdvleuten]

The observability part is the most interesting bit to me.

With agent systems, logs get bad pretty quickly. You want to know what is alive, what spawned what, what it's waiting on, what retried, what died, etc.

Since this is Elixir, are you planning to show the actual BEAM process/supervision structure in WeaveScope, or mostly the higher-level workflow graph?

Feels like both are useful. The graph shows what you meant to run, the process tree shows what is actually running.